Core Concepts
Context Window
The amount of text an AI can consider at once — its short-term memory.
Also known as: context length,context size
The context window is the maximum amount of text (measured in tokens) an AI model can consider at once. Think of it as the model's short-term memory. If a context window is 200,000 tokens, the model can see roughly 150,000 words of input + previous conversation + the response it is generating. In 2026, frontier models have huge context windows: Gemini 3.5 Pro at 2 million tokens, Claude Opus 4.8 at 500,000, GPT-5 at 400,000, Magic.dev at 100+ million. Larger context windows enable workflows that previously required RAG (load an entire book, codebase, or document corpus directly). The trade-off is cost — input tokens are billed per token, so huge prompts get expensive fast.